Home

Awesome

S3PRecon

The official implementation for the CVPR 2023 paper Self-Supervised Super-Plane for Neural 3D Reconstruction.

Installation and Setup

conda env create -f environment.yml
conda activate manhattan

Usage

Training

python train_net.py --cfg_file configs/scannet/0084_self_plane.yaml gpus 0, exp_name scannet_0084_self_plane

Evaluation

python run.py --type evaluate --cfg_file configs/scannet/0084_self_plane.yaml gpus 0, exp_name scannet_0084_self_plane

Mesh extraction

python run.py --type mesh_extract --output_mesh result.obj --cfg_file configs/scannet/0084_self_plane.yaml gpus 0, exp_name scannet_0084_self_plane

Acknowledgments

Citation

If our work is useful for your research, please consider citing:

@inproceedings{ye2023s3p,
  title={Self-Supervised Super-Plane for Neural 3D Reconstruction},
  author={Ye, Botao and Liu, Sifei and Li, Xueting and Yang, Ming-Hsuan},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={21415--21424},
  year={2023}
}